A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services
Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior despite encryption. From packet sizes, directions, timing, and burst structure alone, a passive local observer can infer the serving model, the user's prompt category, and the tas...
Shahrooz Pouryousef, J. Lopez, Saeefa Rubaiyat Nowmi et al.
· 1 citation
· ⚡1